Merge branch 'master' of ssh://git.indexdata.com/home/git/pub/pazpar2

[pazpar2-moved-to-github.git] / doc / pazpar2_conf.xml

diff --git a/doc/pazpar2_conf.xml b/doc/pazpar2_conf.xml
index b3a6281..d425733 100644 (file)
--- a/doc/pazpar2_conf.xml
+++ b/doc/pazpar2_conf.xml
@@ -59,8 +59,9 @@
   
   <refsect2 id="config-server"><title>server</title>
    <para>
   
   <refsect2 id="config-server"><title>server</title>
    <para>

-    This section governs overall behavior of the client. The data
-    elements are described below.
+    This section governs overall behavior of the server. The data
+    elements are described below. From Pazpar2 version 1.2 this is
+    a repeatable element.

    </para>
    <variablelist> <!-- level 1 -->
     <varlistentry>
    </para>
    <variablelist> <!-- level 1 -->
     <varlistentry>

@@ -100,91 +101,30 @@
       </para>
      </listitem>
     </varlistentry>
       </para>
      </listitem>
     </varlistentry>

-    
-    <varlistentry>
-     <term>relevance</term>
-     <listitem>
-      <para>
-       Specifies ICU tokenization and normalization rules
-       for tokens that are used in Pazpar2's relevance ranking.  The 'id'
-       attribute is currently not used, and the 'locale'
-       attribute must be set to one of the locale strings
-       defined in ICU. The child elements listed below can be
-       in any order, except the 'index' element which logically
-       belongs to the end of the list. The stated tokenization,
-       normalization and charmapping instructions are performed
-       in order from top to bottom. 
-      </para>
-      <variablelist> <!-- Level 2 -->
-       <varlistentry><term>casemap</term>
-       <listitem>
-        <para>
-         The attribute 'rule' defines the direction of the
-         per-character casemapping, allowed values are "l"
-         (lower), "u" (upper), "t" (title).  
-        </para>
-       </listitem>
-       </varlistentry>
-       <varlistentry><term>normalize</term>
-       <listitem>
-        <para>
-         Normalization and transformation of tokens follows
-         the rules defined in the 'rule' attribute. For
-         possible values we refer to the extensive ICU
-         documentation found at the 
-         <ulink url="&url.icu.transform;">ICU
-          transformation</ulink> home page. Set filtering
-         principles are explained at the 
-         <ulink url="&url.icu.unicode.set;">ICU set and
-          filtering</ulink> page.
-        </para>
-       </listitem>
-       </varlistentry>
-       <varlistentry><term>tokenize</term>
-       <listitem>
-        <para>
-         Tokenization is the only rule in the ICU chain
-         which splits one token into multiple tokens. The
-         'rule' attribute may have the following values:
-         "s" (sentence), "l" (line-break), "w" (word), and
-         "c" (character), the later probably not being
-         very useful in a pruning Pazpar2 installation. 
-        </para>
-       </listitem>
-       </varlistentry>
-       <varlistentry><term>index</term>
-       <listitem>
-        <para>
-         Finally the 'index' element instruction - without
-         any 'rule' attribute - is used to store the tokens
-         after chain processing in the relevance ranking
-         unit of Pazpar2. It will always be the last
-         instruction in the chain.
-        </para>
-       </listitem>
-       </varlistentry>
-      </variablelist>
-     </listitem>
-    </varlistentry>

 
     <varlistentry>
 
     <varlistentry>

-     <term>sort</term>
+     <term>relevance / sort / mergekey</term>

      <listitem>
       <para>
      <listitem>
       <para>

-       Specifies ICU tokenization and normalization rules
-       for tokens that are used in Pazpar2's sorting. The contents
-       is similar to that of <literal>relevance</literal>.
+       Specifies character set normalization for relevancy / sorting 
+       and the mergekey - for the server. These definitions serves as
+       default for services that don't have these given. For the meaning
+       of these settings refer to the "relevance" element inside service.

       </para>
      </listitem>
     </varlistentry>
     
     <varlistentry>
       </para>
      </listitem>
     </varlistentry>
     
     <varlistentry>

-     <term>mergekey</term>
+     <term>settings</term>

      <listitem>
       <para>
      <listitem>
       <para>

-       Specifies ICU tokenization and normalization rules
-       for tokens that are used in Pazpar2's mergekey. The contents
-       is similar to that of <literal>relevance</literal>.
+       Specifies target settings for the server.. These settings serves
+       as default for all services which don't have these given.
+       The settings element requires one attribute 'src' which specifies
+       a settings file or a directory . If a directory is given all
+       files with suffix <filename>.xml</filename> is read from this
+       directory. Refer to 
+       <xref linkend="target_settings"/> for more information.

       </para>
      </listitem>
     </varlistentry>
       </para>
      </listitem>
     </varlistentry>

@@ -200,7 +140,16 @@
        extraction of data from the internal representation, primarily
        through the 'metadata' sub-element.
       </para>
        extraction of data from the internal representation, primarily
        through the 'metadata' sub-element.
       </para>

-      
+      <para>
+       Pazpar2 version 1.2 and later allows multiple service elements.
+       Multiple services must be given a unique ID by specifying
+       attribute <literal>id</literal>.
+       A single service may be unnamed (service ID omitted). The
+       service ID is referred to in the
+       <link linkend="command-init"><literal>init</literal></link> webservice
+       command's <literal>service</literal> parameter.
+      </para>
+

       <variablelist> <!-- Level 2 -->
        <varlistentry><term>metadata</term>
        <listitem>
       <variablelist> <!-- Level 2 -->
        <varlistentry><term>metadata</term>
        <listitem>

@@ -313,6 +262,16 @@
           </listitem>
          </varlistentry>
 
           </listitem>
          </varlistentry>
 

+         <varlistentry><term>mergekey</term>
+          <listitem>
+           <para>
+            If set to <literal>yes</literal>, the value of this
+            metadata element is appended to the resulting mergekey.
+            By default metadata is not part of a mergekey.
+           </para>
+          </listitem>
+         </varlistentry>
+

          <varlistentry><term>setting</term>
           <listitem>
            <para>
          <varlistentry><term>setting</term>
           <listitem>
            <para>

@@ -327,64 +286,196 @@
              the value to decide how to deal with other data values.
            </para>
            <para>
              the value to decide how to deal with other data values.
            </para>
            <para>

-           </para>

              The purpose of using settings in this way can either be to
              control the behavior of normalization stylesheet in a database-
              dependent way, or to easily make database-dependent values
              available to display-logic in your user interface, without having
              to implement complicated interactions between the user interface
              and your configuration system.
              The purpose of using settings in this way can either be to
              control the behavior of normalization stylesheet in a database-
              dependent way, or to easily make database-dependent values
              available to display-logic in your user interface, without having
              to implement complicated interactions between the user interface
              and your configuration system.

+           </para>

           </listitem>
          </varlistentry>
           </listitem>
          </varlistentry>

+         

         </variablelist> <!-- attributes to metadata -->
         
        </listitem>
        </varlistentry>
         </variablelist> <!-- attributes to metadata -->
         
        </listitem>
        </varlistentry>

+       
+       <varlistentry>
+       <term>relevance</term>
+       <listitem>
+        <para>
+         Specifies ICU tokenization and transformation rules
+         for tokens that are used in Pazpar2's relevance ranking.
+         The 'id' attribute is currently not used, and the 'locale'
+         attribute must be set to one of the locale strings
+         defined in ICU. The child elements listed below can be
+         in any order, except the 'index' element which logically
+         belongs to the end of the list. The stated tokenization,
+         transformation and charmapping instructions are performed
+         in order from top to bottom. 
+        </para>
+        <variablelist> <!-- Level 2 -->
+         <varlistentry><term>casemap</term>
+          <listitem>
+           <para>
+            The attribute 'rule' defines the direction of the
+            per-character casemapping, allowed values are "l"
+            (lower), "u" (upper), "t" (title).  
+           </para>
+          </listitem>
+         </varlistentry>
+         <varlistentry><term>transform</term>
+          <listitem>
+           <para>
+            Normalization and transformation of tokens follows
+            the rules defined in the 'rule' attribute. For
+            possible values we refer to the extensive ICU
+            documentation found at the 
+            <ulink url="&url.icu.transform;">ICU
+             transformation</ulink> home page. Set filtering
+            principles are explained at the 
+            <ulink url="&url.icu.unicode.set;">ICU set and
+             filtering</ulink> page.
+           </para>
+          </listitem>
+         </varlistentry>
+         <varlistentry><term>tokenize</term>
+          <listitem>
+           <para>
+            Tokenization is the only rule in the ICU chain
+            which splits one token into multiple tokens. The
+            'rule' attribute may have the following values:
+            "s" (sentence), "l" (line-break), "w" (word), and
+            "c" (character), the later probably not being
+            very useful in a pruning Pazpar2 installation. 
+           </para>
+          </listitem>
+         </varlistentry>
+        </variablelist>
+        <para>
+         From Pazpar2 version 1.1 the ICU wrapper from YAZ is used.
+         Refer to the <ulink url="&url.yaz.yaz-icu;">yaz-icu</ulink>
+         utility for more information.
+        </para>
+       </listitem>
+       </varlistentry>
+       
+       <varlistentry>
+       <term>sort</term>
+       <listitem>
+        <para>
+         Specifies ICU tokenization and transformation rules
+         for tokens that are used in Pazpar2's sorting. The contents
+         is similar to that of <literal>relevance</literal>.
+        </para>
+       </listitem>
+       </varlistentry>
+       
+       <varlistentry>
+       <term>mergekey</term>
+       <listitem>
+        <para>
+         Specifies ICU tokenization and transformation rules
+         for tokens that are used in Pazpar2's mergekey. The contents
+         is similar to that of <literal>relevance</literal>.
+        </para>
+       </listitem>
+       </varlistentry>
+
+       <varlistentry>
+       <term>settings</term>
+       <listitem>
+        <para>
+         Specifies target settings for this service. Refer to
+         <xref linkend="target_settings"/>.
+        </para>
+       </listitem>
+       </varlistentry>
+
+       <varlistentry>
+       <term>timeout</term>
+       <listitem>
+        <para>
+         Specifies timeout parameters for this service.
+         The <literal>timeout</literal>
+         element supports the following attributes: 
+         <literal>session</literal>, <literal>z3950_operation</literal>,
+         <literal>z3950_session</literal> which specifies
+         'session timeout', 'Z39.50 operation timeout',
+         'Z39.50 session timeout' respectively. The Z39.50 operation
+         timeout is the time Pazpar2 will wait for an active Z39.50/SRU
+         operation before it gives up (times out). The Z39.50 session
+         time out is the time Pazpar2 will keep the session alive for
+         an idle session (no operation).
+        </para>
+        <para>
+         The following is recommended but not required:
+         z3950_operation (30) &lt; session (60) &lt; z3950_session (180) .
+         The default values are given in parantheses.
+        </para>
+       </listitem>
+       </varlistentry>
+

       </variablelist>     <!-- Data elements in service directive -->
      </listitem>
     </varlistentry>
       </variablelist>     <!-- Data elements in service directive -->
      </listitem>
     </varlistentry>

+    

    </variablelist>           <!-- Data elements in server directive -->
   </refsect2>
    </variablelist>           <!-- Data elements in server directive -->
   </refsect2>

-  
+

  </refsect1>
  
  <refsect1><title>EXAMPLE</title>
   <para>Below is a working example configuration:
  </refsect1>
  
  <refsect1><title>EXAMPLE</title>
   <para>Below is a working example configuration:

-  <screen><![CDATA[
-<?xml version="1.0" encoding="UTF-8"?>
-<pazpar2 xmlns="http://www.indexdata.com/pazpar2/1.0">
-
-<server>
-  <listen port="9004"/>
-  <proxy host="us1.indexdata.com" myurl="us1.indexdata.com"/>
-
-  <!-- optional ICU ranking configuration example -->
-  <!--
-  <icu_chain id="el:word" locale="el">
-    <normalize rule="[:Control:] Any-Remove"/>
-    <tokenize rule="l"/>
-    <normalize rule="[[:WhiteSpace:][:Punctuation:]] Remove"/>
-    <casemap rule="l"/>
-    <index/>
-  </icu_chain>
-  -->
-
-  <service>
-    <metadata name="title" brief="yes" sortkey="skiparticle" merge="longest" rank="6"/>
-    <metadata name="isbn" merge="unique"/>
-    <metadata name="date" brief="yes" sortkey="numeric" type="year" merge="range"
-           termlist="yes"/>
-    <metadata name="author" brief="yes" termlist="yes" merge="longest" rank="2"/>
-    <metadata name="subject" merge="unique" termlist="yes" rank="3"/>
-    <metadata name="url" merge="unique"/>
-  </service>
-</server>
-
-</pazpar2>
-]]></screen>
+   <screen><![CDATA[
+    <?xml version="1.0" encoding="UTF-8"?>
+    <pazpar2 xmlns="http://www.indexdata.com/pazpar2/1.0">
+    
+      <server>
+        <listen port="9004"/>
+        <service>
+          <metadata name="title" brief="yes" sortkey="skiparticle"
+             merge="longest" rank="6"/>
+          <metadata name="isbn" merge="unique"/>
+          <metadata name="date" brief="yes" sortkey="numeric"
+             type="year" merge="range" termlist="yes"/>
+          <metadata name="author" brief="yes" termlist="yes"
+             merge="longest" rank="2"/>
+          <metadata name="subject" merge="unique" termlist="yes" rank="3"/>
+          <metadata name="url" merge="unique"/>
+          <relevance>
+            <icu_chain id="relevance" locale="el">
+              <transform rule="[:Control:] Any-Remove"/>
+              <tokenize rule="l"/>
+              <transform rule="[[:WhiteSpace:][:Punctuation:]] Remove"/>
+              <casemap rule="l"/>
+             </icu_chain>
+           </relevance>
+           <settings src="mysettings"/>
+           <timeout session="60"/>
+        <service>
+     </server>
+   </pazpar2>
+    ]]></screen>

   </para>
  </refsect1> 
   </para>
  </refsect1> 

- 
+
+ <refsect1 id="config-include"><title>INCLUDE FACILITY</title>
+  <para>
+   The XML configuration may be partitioned into multiple files by using
+   the <literal>include</literal> element which takes a single attribute,
+   <literal>src</literal>. The of the <literal>src</literal> attribute is
+   regular Shell like glob-pattern. For example,
+   <screen><![CDATA[
+    <include src="/etc/pazpar2/conf.d/*.xml"/>
+    ]]></screen>
+  </para>
+  <para>
+   The include facility requires Pazpar2 version 1.2.
+  </para>
+ </refsect1>
+

  <refsect1 id="target_settings"><title>TARGET SETTINGS</title>
   <para>
    Pazpar2 features a cunning scheme by which you can associate various
  <refsect1 id="target_settings"><title>TARGET SETTINGS</title>
   <para>
    Pazpar2 features a cunning scheme by which you can associate various

@@ -420,7 +511,9 @@
    environment, where different end-users may need to be represented to
    some search targets in different ways. This, again, can be managed
    using an external database or other lookup mechanism. Setting overrides
    environment, where different end-users may need to be represented to
    some search targets in different ways. This, again, can be managed
    using an external database or other lookup mechanism. Setting overrides

-   can be performed either using the 'init' or the 'settings' webservice
+   can be performed either using the
+   <link linkend="command-init">init</link> or the 
+   <link linkend="command-settings">settings</link> webservice

    command.
   </para>
   
    command.
   </para>
   

@@ -433,8 +526,10 @@
   
   <para>
    Finally, as an extreme case of this, the webservice client can
   
   <para>
    Finally, as an extreme case of this, the webservice client can

-   introduce entirely new targets, on the fly, as part of the init or
-   settings command. This is useful if you desire to manage information
+   introduce entirely new targets, on the fly, as part of the
+   <link linkend="command-init">init</link> or
+   <link linkend="command-settings">settings</link> command.
+   This is useful if you desire to manage information

    about your search targets in a separate application such as a database.
    You do not need any static settings file whatsoever to run Pazpar2 -- as
    long as the webservice client is prepared to supply the necessary
    about your search targets in a separate application such as a database.
    You do not need any static settings file whatsoever to run Pazpar2 -- as
    long as the webservice client is prepared to supply the necessary

@@ -739,6 +834,20 @@
        Provides the path of an XSLT stylesheet which will be used to
        map incoming records to the internal representation.
       </para>
        Provides the path of an XSLT stylesheet which will be used to
        map incoming records to the internal representation.
       </para>

+      <para>
+       When mapping MARC XML records, XSLT can be bypassed for increased 
+       performance with the alternate "MARC map" format.  Provide the
+       path of a file with extension ".mmap" containing on each line:
+       <programlisting>
+        &lt;field&gt; &lt;subfield&gt; &lt;metadata element&gt;</programlisting>
+       For example:
+       <programlisting>
+        245 a title
+        500 $ description
+        773 * citation</programlisting>
+       To map the field value specify a subfield of '$'.  To store a 
+       concatenation of all subfields, specify a subfield of '*'.
+      </para>

      </listitem>
     </varlistentry>
     <varlistentry>
      </listitem>
     </varlistentry>
     <varlistentry>

@@ -837,20 +946,30 @@
        </para>
       </listitem>
     </varlistentry>
        </para>
       </listitem>
     </varlistentry>

+
+    <varlistentry>
+      <term>pz:sort</term>
+      <listitem>
+        <para>
+         Specifies sort criteria to be applied to the result set. Only works for targets
+         which support the sort service.
+       </para>
+      </listitem>
+    </varlistentry>

    </variablelist>
   </refsect2>
 
  </refsect1>
  <refsect1><title>SEE ALSO</title>
   <para>
    </variablelist>
   </refsect2>
 
  </refsect1>
  <refsect1><title>SEE ALSO</title>
   <para>

-   Pazpar2:

    <citerefentry>
     <refentrytitle>pazpar2</refentrytitle>
     <manvolnum>8</manvolnum>
    </citerefentry>
    <citerefentry>
     <refentrytitle>pazpar2</refentrytitle>
     <manvolnum>8</manvolnum>
    </citerefentry>

-  </para>
-  <para>
-   Pazpar2 protocol:
+   <citerefentry>
+    <refentrytitle>yaz-icu</refentrytitle>
+    <manvolnum>1</manvolnum>
+   </citerefentry>

    <citerefentry>
     <refentrytitle>pazpar2_protocol</refentrytitle>
     <manvolnum>7</manvolnum>
    <citerefentry>
     <refentrytitle>pazpar2_protocol</refentrytitle>
     <manvolnum>7</manvolnum>